Work

Leveraging Artificial Intelligence-Powered Virtual Assistant for Information Retrieval in Indigenous Agriculture: Insights from Nigeria

Year: 2025

Type: conference-paper

Abstract: This study examines the use of an AI-powered Virtual Assistant (VA) to aid information retrieval in the cultivation of indigenous vegetables in Nigeria. A two-phase approach involved a needs assessment with 240 youth and the deployment of a bilingual web-based VA using a Large Language Model. The results show a strong youth interest in the tool, despite infrastructure and financial challenges. The VA achieved a high Precision@3 score (0.87), indicating its potential to improve agricultural decision-making in low-resource areas. The use of the VA can improve access to timely and context-specific agricultural knowledge, thereby supporting climate change adaptation and contributing to global food security.

Source: International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR)

DOI: 10.1145/3726302.3730265